default_mma_core_sm75.h File Reference

Defines basic properties needed by CTA-level GEMMs assuming expectations about data layout of the global memory fragments, data types, and internal tile sizes. More...

#include "cutlass/cutlass.h"
#include "cutlass/array.h"
#include "cutlass/platform/platform.h"
#include "cutlass/numeric_types.h"
#include "cutlass/matrix_shape.h"
#include "cutlass/layout/tensor_op_multiplicand_sm75.h"
#include "cutlass/transform/pitch_linear_thread_map.h"
#include "cutlass/transform/threadblock/regular_tile_iterator_tensor_op.h"
#include "cutlass/gemm/warp/default_mma_tensor_op.h"
#include "cutlass/gemm/threadblock/default_mma_core.h"

Include dependency graph for default_mma_core_sm75.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes
struct	cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >
struct	cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >
struct	cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >
struct	cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >
struct	cutlass::gemm::threadblock::DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor >

Namespaces
	cutlass
	cutlass::gemm
	cutlass::gemm::threadblock

Detailed Description

Partial specializations for threadblock::Mma operations targeting TensorOp instructions.